Asaia (oligotyping)

Load packages, paths, functions

# Load main packages, paths and custom functions
source("../../../source/main_packages.R")
source("../../../source/paths.R")
source("../../../source/functions.R")

# Load supplementary packages
packages <- c("RColorBrewer", "ggpubr", "cowplot", "Biostrings", "openxlsx", "kableExtra")
invisible(lapply(packages, require, character.only = TRUE))

Preparation

Tables preparation

Seqtab

# move to oligotyping directory
setwd(paste0(path_oligo,"/asaia/oligotyping_Asaia_sequences-c5-s1-a0.0-A0-M10"))

# load the matrix count table
matrix_count <- read.table("MATRIX-COUNT.txt", header = TRUE) %>% t()

# arrange it
colnames(matrix_count) <- matrix_count[1,]
matrix_count <- matrix_count[-1,]
matrix_count <- matrix_count %>% as.data.frame()

# print it
matrix_count %>%
  kbl() %>%
  kable_paper("hover", full_width = F)
CTC1 CTC10 CTC11 CTC12 CTC13 CTC14 CTC15 CTC2 CTC3 CTC4 CTC5 CTC6 CTC7 CTC9 NP14 NP2 NP20 NP27 NP29 NP30 NP34 NP35 NP36 NP37 NP38 NP39 NP41 NP42 NP43 NP44 NP5 NP8 S126 S147 S154 S18 S19 S20 S21 S22 S23 S24 S25 S26 S27 S28 S29 S30 S31 S32 S33 S34 S35 S36 S37 S38 S39 S40 S42 S44 S45 S46 S47 S48 S49 S50 S51 S52
TGCGA 0 1 1 0 8 0 0 0 1 1 0 2 0 0 32 0 70 0 73 70 11 8 221 153738 118463 81849 97920 46367 64795 135582 0 0 0 0 0 0 2 0 0 0 0 1 1 0 6 0 0 0 1 1 0 0 0 7 10 5 15 18 0 8 0 0 0 0 0 32 0 0
CATAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 31 0 0 1 58 56 8 7 2 2744 129509 116951 141940 121248 146560 1893 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TACGA 57 315 647 156 2206 18 133 9 567 377 1 2165 12 88 6 390 1 5 43 13 8 11 7 196884 20230 16952 3701 15217 22358 17187 1 16 1 1 2 17 1277 67 195 21 33 468 108 109 866 105 1 1006 1355 1772 2848 1817 5507 6828 9095 3991 18210 20197 1 24 46 24 84 85 105 182 310 298
TGCGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 5 4 0 0 2 718 627 479 857 452 679 1193 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CATGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 35 779 731 1039 900 1113 21 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TACGG 0 2 0 0 5 0 0 0 1 1 0 7 0 0 0 3 0 0 1 7 0 0 0 844 175 112 72 153 308 157 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 2 0 2 0 2 7 2 4 26 20 0 0 0 0 0 0 0 0 0 0
CATAA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 25 72 52 59 70 1 0 0 0 0 0 0 7 2 3 0 1 10 2 4 3 4 0 23 55 93 68 27 193 55 87 31 92 359 0 0 1 0 1 1 3 0 0 5
CGTAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 2 0 0 0 1 99 138 169 134 242 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CGCGA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 74 78 111 89 29 53 174 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CATGA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 35 33 135 45 44 61 13 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 1 0 0 2 0 0 0 0 0 0 0 0 0 0
TGCAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 17 31 116 64 36 55 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CGTGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 1 0 0 0 4 57 33 67 74 82 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TATAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 11 66 59 56 60 63 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TGTGA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 67 62 27 41 22 44 45 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TGCAA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 81 26 26 38 20 23 63 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TATGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 21 45 27 33 51 35 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CACAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 16 41 38 37 38 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TATGA 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0 0 43 13 12 20 18 16 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 4 0 0 0 6 4 4 6 4 0 0 0 0 0 0 0 0 0 0
CACGA 0 0 0 0 3 0 0 0 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 62 19 7 4 5 14 5 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 0 0 1 0 0 0 0 0 2 4 0 15 9 0 0 0 0 0 0 0 0 0 0
TACAA 0 0 1 0 1 0 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 72 2 8 3 6 9 5 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 3 2 11 0 6 19 0 0 0 0 0 0 0 0 0 1
TGTGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 13 24 10 18 39 27 7 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TACAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 21 7 31 2 17 23 5 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TGCTA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 12 10 11 22 11 11 26 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TACTA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 22 4 5 3 0 6 3 0 0 0 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 2 3 1 1 4 2 6 0 10 23 0 0 0 0 0 0 1 0 0 0
CGCGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 5 10 6 14 14 18 6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CTTAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 10 11 11 12 19 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CACGG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 4 6 5 10 7 12 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TGTAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 6 3 3 5 15 4 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
GGCGA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 25 0 7 2 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CATAT 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 20 2 4 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CGTGA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 5 0 8 4 3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
AATAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3 3 3 6 4 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
TATAA 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 1 5 3 7 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
CGCAG 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 3 2 3 3 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0

Taxonomy

# move to oligotyping directory
setwd(paste0(path_oligo,"/asaia/oligotyping_Asaia_sequences-c5-s1-a0.0-A0-M10"))

# load the fasta table
fasta <- readDNAStringSet("OLIGO-REPRESENTATIVES.fasta")

# arrange it
fasta <- fasta %>% as.data.frame()
colnames(fasta) <- "seq"
fasta$oligotype <- rownames(fasta)
fasta <- fasta %>% dplyr::select(-c(seq))

# print it
fasta %>%
  kbl() %>%
  kable_paper("hover", full_width = F)
oligotype
TGCGA TGCGA
CATAG CATAG
TACGA TACGA
TGCGG TGCGG
CATGG CATGG
TACGG TACGG
CATAA CATAA
CGTAG CGTAG
CGCGA CGCGA
CATGA CATGA
TGCAG TGCAG
CGTGG CGTGG
TATAG TATAG
TGTGA TGTGA
TGCAA TGCAA
TATGG TATGG
CACAG CACAG
TATGA TATGA
CACGA CACGA
TACAA TACAA
TGTGG TGTGG
TACAG TACAG
TGCTA TGCTA
TACTA TACTA
CGCGG CGCGG
CTTAG CTTAG
CACGG CACGG
TGTAG TGTAG
GGCGA GGCGA
CATAT CATAT
CGTGA CGTGA
AATAG AATAG
TATAA TATAA
CGCAG CGCAG

Change oligotype name by oligotype / MED nodes in the matrix count

# Reference file 

## move to tsv directory
setwd(path_tsv)

## load the reference table
ref_oligo_med2 <- read.table("2B_REF_info_asaia.tsv", sep="\t", header = TRUE)

## select only the 5 oligotypes of Asaia
ref_oligo_med2 <- ref_oligo_med2[!is.na(ref_oligo_med2$oligotype),]

## change order of columns
ref_oligo_med2 <- ref_oligo_med2 %>% select(c(seq, oligotype, MED_node_frequency_size, OLIGO_oligotype_frequency_size))

## create a column with reference name (will be used in plots)
ref_oligo_med2$ref <- paste0("oligotype_", ref_oligo_med2$OLIGO_oligotype_frequency_size, " / node_", ref_oligo_med2$MED_node_frequency_size)

## create a copy of fasta 
fasta2 <- fasta

# Matrix count

## create an oligotype column in the matrix count
matrix_count$oligotype <- rownames(matrix_count)

## change order of columns
matrix_count <- matrix_count %>% dplyr::select(c(oligotype, everything()))

## merge the matrix count and the reference dataframe
matrix_count2 <- matrix_count %>% merge(ref_oligo_med2 %>% dplyr::select(-c(seq)), by="oligotype")

## change order of columns
matrix_count2 <- matrix_count2 %>% dplyr::select(c(oligotype, MED_node_frequency_size, OLIGO_oligotype_frequency_size, ref, everything()))

## change rownames
rownames(matrix_count2) <- matrix_count2$ref

## change order of columns
matrix_count2 <- matrix_count2 %>% dplyr::select(-c(oligotype, ref, MED_node_frequency_size, OLIGO_oligotype_frequency_size))

## print it
matrix_count2 %>%
  kbl() %>%
  kable_paper("hover", full_width = F)
CTC1 CTC10 CTC11 CTC12 CTC13 CTC14 CTC15 CTC2 CTC3 CTC4 CTC5 CTC6 CTC7 CTC9 NP14 NP2 NP20 NP27 NP29 NP30 NP34 NP35 NP36 NP37 NP38 NP39 NP41 NP42 NP43 NP44 NP5 NP8 S126 S147 S154 S18 S19 S20 S21 S22 S23 S24 S25 S26 S27 S28 S29 S30 S31 S32 S33 S34 S35 S36 S37 S38 S39 S40 S42 S44 S45 S46 S47 S48 S49 S50 S51 S52
oligotype_CATAG (16) | size:661010 / node_N1156 (40) | size:622340 0 0 0 0 0 0 0 0 0 0 0 0 0 0 31 0 0 1 58 56 8 7 2 2744 129509 116951 141940 121248 146560 1893 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
oligotype_CATGG (8) | size:4619 / node_N0492 (18) | size:6153 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 35 779 731 1039 900 1113 21 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
oligotype_TACGA (68) | size:376837 / node_N0939 (68) | size:364329 57 315 647 156 2206 18 133 9 567 377 1 2165 12 88 6 390 1 5 43 13 8 11 7 196884 20230 16952 3701 15217 22358 17187 1 16 1 1 2 17 1277 67 195 21 33 468 108 109 866 105 1 1006 1355 1772 2848 1817 5507 6828 9095 3991 18210 20197 1 24 46 24 84 85 105 182 310 298
oligotype_TGCGA (33) | size:699320 / node_N1147 (33) | size:651167 0 1 1 0 8 0 0 0 1 1 0 2 0 0 32 0 70 0 73 70 11 8 221 153738 118463 81849 97920 46367 64795 135582 0 0 0 0 0 0 2 0 0 0 0 1 1 0 6 0 0 0 1 1 0 0 0 7 10 5 15 18 0 8 0 0 0 0 0 32 0 0
oligotype_TGCGG (10) | size:5016 / node_N1146 (10) | size:4924 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 5 4 0 0 2 718 627 479 857 452 679 1193 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 
## edit the fasta dataframe
fasta2 <- fasta2 %>% merge(ref_oligo_med2 %>% dplyr::select(-c(seq)), by="oligotype")
rownames(fasta2) <- fasta2$ref
fasta2 <- fasta2 %>% dplyr::select(-c(MED_node_frequency_size, OLIGO_oligotype_frequency_size, oligotype))

## print it
fasta2 %>%
  kbl() %>%
  kable_paper("hover", full_width = F)
ref
oligotype_CATAG (16) | size:661010 / node_N1156 (40) | size:622340 oligotype_CATAG (16) | size:661010 / node_N1156 (40) | size:622340
oligotype_CATGG (8) | size:4619 / node_N0492 (18) | size:6153 oligotype_CATGG (8) | size:4619 / node_N0492 (18) | size:6153
oligotype_TACGA (68) | size:376837 / node_N0939 (68) | size:364329 oligotype_TACGA (68) | size:376837 / node_N0939 (68) | size:364329
oligotype_TGCGA (33) | size:699320 / node_N1147 (33) | size:651167 oligotype_TGCGA (33) | size:699320 / node_N1147 (33) | size:651167
oligotype_TGCGG (10) | size:5016 / node_N1146 (10) | size:4924 oligotype_TGCGG (10) | size:5016 / node_N1146 (10) | size:4924

Metadata

metadata <- read.csv(paste0(path_metadata,"/metadata_08_02_2021.csv"), sep=";")
rownames(metadata) <- metadata$Sample

Phyloseq object with oligotypes

# convert matrix_count into matrix and numeric
matrix_count <- matrix_count2 %>% as.matrix()
class(matrix_count) <- "numeric"

# phyloseq elements
OTU = otu_table(as.matrix(matrix_count), taxa_are_rows =TRUE)
TAX = tax_table(as.matrix(fasta2))
SAM = sample_data(metadata)

# phyloseq object
ps <- phyloseq(OTU, TAX, SAM)
ps
## phyloseq-class experiment-level object
## otu_table()   OTU Table:         [ 5 taxa and 68 samples ]
## sample_data() Sample Data:       [ 68 samples by 15 sample variables ]
## tax_table()   Taxonomy Table:    [ 5 taxa by 1 taxonomic ranks ]
compute_read_counts(ps)
## [1] 1746802
# remove blanks
ps <- subset_samples(ps, Location!="Blank")
ps <- check_ps(ps)
ps
## phyloseq-class experiment-level object
## otu_table()   OTU Table:         [ 5 taxa and 67 samples ]
## sample_data() Sample Data:       [ 67 samples by 15 sample variables ]
## tax_table()   Taxonomy Table:    [ 5 taxa by 1 taxonomic ranks ]

Create new metadata with Percent

Load ps with all samples (for final plot)

setwd(path_rdata)
ps.filter <- readRDS("1D_MED_phyloseq_decontam.rds")
ps.filter <- check_ps(ps.filter)

Edit new metadata with Percent_asaia

guide_italics <- guides(fill = guide_legend(label.theme = element_text(size = 16, face = "italic", colour = "Black", angle = 0)))

# add read depth in sample table of phyloseq object
sample_data(ps.filter)$Read_depth <- sample_sums(ps.filter)

# select Wolbachia
ps.asaia <- ps.filter %>% subset_taxa(Genus=="Asaia")

# add read depth of Wolbachia
sample_data(ps.filter)$Read_asaia <- sample_sums(ps.asaia)
sample_data(ps.filter) %>% colnames()
##  [1] "Sample"      "Well"        "Primer1"     "Primer2"     "Location"   
##  [6] "Field"       "Country"     "Organ"       "Species"     "Individual" 
## [11] "Individuals" "Date"        "Run"         "Control"     "Dna"        
## [16] "Read_depth"  "Read_asaia"
sample_data(ps.asaia) %>% colnames()
##  [1] "Sample"      "Well"        "Primer1"     "Primer2"     "Location"   
##  [6] "Field"       "Country"     "Organ"       "Species"     "Individual" 
## [11] "Individuals" "Date"        "Run"         "Control"     "Dna"        
## [16] "Read_depth"
# add percent of Wolbachia
sample_data(ps.filter)$Percent_asaia <- sample_data(ps.filter)$Read_asaia / sample_data(ps.filter)$Read_depth

# round the percent of Wolbachia at 2 decimals
sample_data(ps.filter)$Percent_asaia <- sample_data(ps.filter)$Percent_asaia %>% round(2)

# extract metadata table
test <- data.frame(sample_data(ps.filter))

# merge this metadata table with the other
new.metadata <- data.frame(sample_data(ps)) %>% merge(test %>% dplyr::select(c(Sample, Read_depth, Read_asaia, Percent_asaia)), by="Sample")
new.metadata <- test[new.metadata$Sample %in% sample_names(ps),]
rownames(new.metadata) <- new.metadata$Sample

# print it
new.metadata %>%
  kbl() %>%
  kable_paper("hover", full_width = F)
Sample Well Primer1 Primer2 Location Field Country Organ Species Individual Individuals Date Run Control Dna Read_depth Read_asaia Percent_asaia
CTC1 CTC1 G5 V4-SA707 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 29779 57 0.00
CTC10 CTC10 D6 V4-SA704 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 37,9 2609 318 0.12
CTC11 CTC11 E6 V4-SA705 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 13874 649 0.05
CTC12 CTC12 F6 V4-SA706 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 40,1 1146 156 0.14
CTC13 CTC13 G6 V4-SA707 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 18035 2224 0.12
CTC14 CTC14 H6 V4-SA708 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 6,17 1708 18 0.01
CTC15 CTC15 I6 V4-SA709 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 23180 133 0.01
CTC2 CTC2 H5 V4-SA708 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 30692 9 0.00
CTC3 CTC3 I5 V4-SA709 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 39920 569 0.01
CTC4 CTC4 J5 V4-SA710 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 1,15 2139 380 0.18
CTC5 CTC5 K5 V4-SA711 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 15789 1 0.00
CTC6 CTC6 L5 V4-SA712 V3-SA505 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 58 19753 2178 0.11
CTC9 CTC9 C6 V4-SA703 V3-SA506 Wolbachia - Lab France Whole Culex quinquefasciatus N/A 0 09/03/2018 run2 True sample 33,6 4980 88 0.02
NP14 NP14 K4 V4-SA711 V3-SA504 Guadeloupe Field Guadeloupe Ovary Aedes aegypti 1a 0 N/A run3 True sample 0,437 7973 69 0.01
NP2 NP2 K3 V4-SA711 V3-SA503 Guadeloupe Field Guadeloupe Ovary Culex quinquefasciatus 1c 0 N/A run3 True sample 41,6 648335 394 0.00
NP20 NP20 E5 V4-SA705 V3-SA505 Guadeloupe Field Guadeloupe Ovary Aedes aegypti 3a 0 N/A run3 True sample 0,357 136 71 0.52
NP27 NP27 L5 V4-SA712 V3-SA505 Guadeloupe Field Guadeloupe Whole Culex quinquefasciatus 7c 0 N/A run3 True sample 1,16 1234 6 0.00
NP29 NP29 B6 V4-SA702 V3-SA506 Guadeloupe Field Guadeloupe Whole Culex quinquefasciatus 9c 0 N/A run3 True sample 0,314 203 184 0.91
NP30 NP30 C6 V4-SA703 V3-SA506 Guadeloupe Field Guadeloupe Whole Culex quinquefasciatus 10c 0 N/A run3 True sample 0,666 228 155 0.68
NP34 NP34 G6 V4-SA707 V3-SA506 Guadeloupe Field Guadeloupe Whole Culex quinquefasciatus 14c 0 N/A run3 True sample 0,486 95 27 0.28
NP35 NP35 H6 V4-SA708 V3-SA506 Guadeloupe Field Guadeloupe Whole Aedes aegypti 7a 0 N/A run3 True sample 4,64 196532 26 0.00
NP36 NP36 I6 V4-SA709 V3-SA506 Guadeloupe Field Guadeloupe Whole Aedes aegypti 8a 0 N/A run3 True sample 1,06 249 232 0.93
NP37 NP37 J6 V4-SA710 V3-SA506 Guadeloupe Field Guadeloupe Whole Aedes aegypti 9a 0 N/A run3 True sample 22,7 419340 355588 0.85
NP38 NP38 K6 V4-SA711 V3-SA506 Guadeloupe Field Guadeloupe Whole Aedes aegypti 10a 0 N/A run3 True sample 3,88 282479 270454 0.96
NP39 NP39 L6 V4-SA712 V3-SA506 Guadeloupe Field Guadeloupe Whole Aedes aegypti 11a 0 N/A run3 True sample 20,2 218684 218013 1.00
NP41 NP41 B7 V4-SA702 V3-SA507 Guadeloupe Field Guadeloupe Whole Aedes aegypti 13a 0 N/A run3 True sample 5,32 247152 246366 1.00
NP42 NP42 C7 V4-SA703 V3-SA507 Guadeloupe Field Guadeloupe Whole Aedes aegypti 14a 0 N/A run3 True sample 4,65 185157 185069 1.00
NP43 NP43 D7 V4-SA704 V3-SA507 Guadeloupe Field Guadeloupe Whole Aedes aegypti 15a 0 N/A run3 True sample 6,89 239335 236790 0.99
NP44 NP44 E7 V4-SA705 V3-SA507 Guadeloupe Field Guadeloupe Whole Aedes aegypti 16a 0 N/A run3 True sample 21,7 156879 156424 1.00
NP5 NP5 B4 V4-SA702 V3-SA504 Guadeloupe Field Guadeloupe Ovary Culex quinquefasciatus 2c 0 N/A run3 True sample 33,5 736159 2 0.00
NP8 NP8 E4 V4-SA705 V3-SA504 Guadeloupe Field Guadeloupe Ovary Culex quinquefasciatus 3c 0 N/A run3 True sample 46 334799 17 0.00
S100 S100 K7 V4-SA711 V3-SA507 Camping Europe Field France Ovary Culex pipiens GL1 1 30/05/2017 run1 True sample 8,02 52486 0 0.00
S102 S102 A8 V4-SA701 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL2 2 30/05/2017 run1 True sample 0,241 3456 0 0.00
S104 S104 C8 V4-SA703 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL5 5 30/05/2017 run1 True sample 24,1 52403 0 0.00
S105 S105 D8 V4-SA704 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL6 6 30/05/2017 run1 True sample 6,83 55577 0 0.00
S106 S106 E8 V4-SA705 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL7 7 30/05/2017 run1 True sample 51 33053 0 0.00
S107 S107 F8 V4-SA706 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL8 8 30/05/2017 run1 True sample 32,6 52154 0 0.00
S108 S108 G8 V4-SA707 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL9 9 30/05/2017 run1 True sample 32,2 55735 0 0.00
S109 S109 H8 V4-SA708 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL10 10 30/05/2017 run1 True sample 26,5 59023 0 0.00
S110 S110 I8 V4-SA709 V3-SA508 Camping Europe Field France Ovary Culex pipiens GL11 0 30/05/2017 run1 True sample 27,5 57377 0 0.00
S121 S121 H1 V4-SA708 V3-SA501 Bosc Field France Ovary Culex pipiens J26 22 28/06/2017 run2 True sample 12,7 20361 0 0.00
S122 S122 I1 V4-SA709 V3-SA501 Bosc Field France Ovary Culex pipiens J27 23 28/06/2017 run2 True sample 22,7 9803 0 0.00
S123 S123 J1 V4-SA710 V3-SA501 Bosc Field France Ovary Culex pipiens J28 24 28/06/2017 run2 True sample 6,41 20130 0 0.00
S124 S124 K1 V4-SA711 V3-SA501 Bosc Field France Ovary Culex pipiens J29 25 28/06/2017 run2 True sample 33,9 18146 0 0.00
S126 S126 K6 V4-SA711 V3-SA506 Bosc Field France Ovary Culex pipiens J30 26 28/06/2017 run2 True sample 58 15235 1 0.00
S127 S127 B2 V4-SA702 V3-SA502 Bosc Field France Ovary Culex pipiens J31 27 28/06/2017 run2 True sample 12,8 24696 0 0.00
S128 S128 C2 V4-SA703 V3-SA502 Bosc Field France Ovary Culex pipiens J32 28 28/06/2017 run2 True sample 35,1 16305 0 0.00
S146 S146 I3 V4-SA709 V3-SA503 Lavar (labo) Lab France Ovary Culex pipiens MW52 29 29/08/2017 run2 True sample 35,2 25012 0 0.00
S147 S147 J3 V4-SA710 V3-SA503 Lavar (labo) Lab France Ovary Culex pipiens MW53 30 29/08/2017 run2 True sample 27,1 25171 1 0.00
S148 S148 K3 V4-SA711 V3-SA503 Lavar (labo) Lab France Ovary Culex pipiens MW54 31 29/08/2017 run2 True sample 43,2 14164 0 0.00
S150 S150 A4 V4-SA701 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW55 32 29/08/2017 run2 True sample 2,3 15081 0 0.00
S151 S151 B4 V4-SA702 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW56 33 29/08/2017 run2 True sample 38,8 22944 0 0.00
S152 S152 C4 V4-SA703 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW57 34 29/08/2017 run2 True sample 39,8 15082 0 0.00
S153 S153 D4 V4-SA704 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW58 35 29/08/2017 run2 True sample 52 17040 0 0.00
S154 S154 E4 V4-SA705 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW59 36 29/08/2017 run2 True sample 37,7 9626 2 0.00
S160 S160 K4 V4-SA711 V3-SA504 Lavar (labo) Lab France Ovary Culex pipiens MW60 37 29/08/2017 run2 True sample 58 72508 0 0.00
S162 S162 B5 V4-SA702 V3-SA505 Lavar (labo) Lab France Ovary Culex pipiens MW61 38 29/08/2017 run2 True sample 42 25180 0 0.00
S163 S163 L6 V4-SA712 V3-SA506 Lavar (labo) Lab France Ovary Culex pipiens MW62 39 30/08/2017 run2 True sample 51 12333 0 0.00
S164 S164 C5 V4-SA703 V3-SA505 Lavar (labo) Lab France Ovary Culex pipiens MW63 40 30/08/2017 run2 True sample 36,6 22368 0 0.00
S165 S165 D5 V4-SA704 V3-SA505 Lavar (labo) Lab France Ovary Culex pipiens MW64 41 30/08/2017 run2 True sample 53 17731 0 0.00
S166 S166 E5 V4-SA705 V3-SA505 Camping Europe Field France Ovary Culex pipiens GL4 4 30/05/2017 run2 True sample 23,1 13979 0 0.00
S167 S167 F5 V4-SA706 V3-SA505 Bosc Field France Ovary Culex pipiens J32 28 28/06/2017 run2 True sample 29,1 14048 0 0.00
S169 S169 B7 V4-SA702 V3-SA507 Camping Europe Field France Ovary Culex pipiens 5 43 16/05/2017 run2 True sample 5,84 11553 0 0.00
S170 S170 C7 V4-SA703 V3-SA507 Camping Europe Field France Ovary Culex pipiens 6 44 16/05/2017 run2 True sample 5,55 8852 0 0.00
S18 S18 A1 V4-SA701 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW75 0 30/08/2017 run1 True sample 0,089 4290 17 0.00
S19 S19 B1 V4-SA702 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW65 0 30/08/2017 run1 True sample 21,9 44527 1288 0.03
S20 S20 C1 V4-SA703 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW66 0 30/08/2017 run1 True sample 16,6 42864 69 0.00
S21 S21 D1 V4-SA704 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW67 0 30/08/2017 run1 True sample 12,4 33798 198 0.01
S22 S22 E1 V4-SA705 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW68 0 30/08/2017 run1 True sample 24,1 19044 21 0.00
S23 S23 F1 V4-SA706 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW69 0 30/08/2017 run1 True sample 20,8 38172 34 0.00
S24 S24 G1 V4-SA707 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW70 0 30/08/2017 run1 True sample 34,2 42355 479 0.01
S25 S25 H1 V4-SA708 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW71 0 30/08/2017 run1 True sample 21,9 47688 111 0.00
S26 S26 I1 V4-SA709 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW72 0 30/08/2017 run1 True sample 0,322 5394 113 0.02
S27 S27 J1 V4-SA710 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW73 0 30/08/2017 run1 True sample 11,3 24558 879 0.04
S28 S28 A2 V4-SA701 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW74 0 30/08/2017 run1 True sample 0,112 4503 109 0.02
S30 S30 K1 V4-SA711 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW1 0 23/08/2017 run1 True sample 4,43 25353 1032 0.04
S31 S31 L1 V4-SA712 V3-SA501 Lavar (labo) Lab France Whole Culex pipiens MW2 0 23/08/2017 run1 True sample 2,66 20417 1416 0.07
S32 S32 C2 V4-SA703 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW3 0 23/08/2017 run1 True sample 0,504 12441 1873 0.15
S33 S33 D2 V4-SA704 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW4 0 23/08/2017 run1 True sample 0,782 33867 2919 0.09
S34 S34 E2 V4-SA705 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW5 0 23/08/2017 run1 True sample 1,38 9367 1845 0.20
S35 S35 F2 V4-SA706 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW6 0 23/08/2017 run1 True sample 0,56 11663 5709 0.49
S36 S36 G2 V4-SA707 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW7 0 23/08/2017 run1 True sample 39,8 33020 6912 0.21
S37 S37 H2 V4-SA708 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW8 0 23/08/2017 run1 True sample 41,3 18340 9220 0.50
S38 S38 I2 V4-SA709 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW9 0 23/08/2017 run1 True sample 32,1 54790 4036 0.07
S39 S39 J2 V4-SA710 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW10 0 23/08/2017 run1 True sample 37,3 36273 18381 0.51
S40 S40 K2 V4-SA711 V3-SA502 Lavar (labo) Lab France Whole Culex pipiens MW11 0 23/08/2017 run1 True sample 4,58 44448 20654 0.46
S42 S42 A3 V4-SA701 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE1 0 30/05/2017 run1 True sample 0 4107 1 0.00
S43 S43 B3 V4-SA702 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE2 0 30/05/2017 run1 True sample 0,191 9279 0 0.00
S44 S44 C3 V4-SA703 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE3 0 30/05/2017 run1 True sample 0,102 8026 32 0.00
S45 S45 D3 V4-SA704 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE4 0 30/05/2017 run1 True sample 0,223 18150 47 0.00
S47 S47 F3 V4-SA706 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE6 0 30/05/2017 run1 True sample 0,291 1951 85 0.04
S48 S48 G3 V4-SA707 V3-SA503 Camping Europe Field France Whole Culex pipiens GLE7 0 30/05/2017 run1 True sample 3,44 56738 86 0.00
S49 S49 H3 V4-SA708 V3-SA503 Bosc Field France Whole Culex pipiens E1 0 28/06/2017 run1 True sample 1,1 33498 109 0.00
S50 S50 I3 V4-SA709 V3-SA503 Bosc Field France Whole Culex pipiens E2 0 28/06/2017 run1 True sample 0,771 28481 214 0.01
S51 S51 J3 V4-SA710 V3-SA503 Bosc Field France Whole Culex pipiens E3 0 28/06/2017 run1 True sample 17,8 61788 310 0.01
S52 S52 K3 V4-SA711 V3-SA503 Bosc Field France Whole Culex pipiens E4 0 28/06/2017 run1 True sample 0,495 21553 304 0.01
S55 S55 B4 V4-SA702 V3-SA504 Bosc Field France Whole Culex pipiens E6 0 28/06/2017 run1 True sample 2,85 50447 0 0.00
S56 S56 C4 V4-SA703 V3-SA504 Bosc Field France Whole Culex pipiens E7 0 28/06/2017 run1 True sample 3,6 42609 0 0.00
S57 S57 D4 V4-SA704 V3-SA504 Bosc Field France Whole Culex pipiens E8 0 28/06/2017 run1 True sample 4,92 49157 0 0.00
S58 S58 E4 V4-SA705 V3-SA504 Bosc Field France Whole Culex pipiens E9 0 28/06/2017 run1 True sample 1,63 30357 0 0.00
S59 S59 F4 V4-SA706 V3-SA504 Bosc Field France Whole Culex pipiens E10 0 28/06/2017 run1 True sample 1,64 32798 0 0.00
S60 S60 G4 V4-SA707 V3-SA504 Bosc Field France Whole Culex pipiens E11 0 28/06/2017 run1 True sample 2,7 44485 0 0.00
S61 S61 H4 V4-SA708 V3-SA504 Bosc Field France Whole Culex pipiens E12 0 28/06/2017 run1 True sample 2 49545 0 0.00
S63 S63 J4 V4-SA710 V3-SA504 Bosc Field France Whole Culex pipiens E14 0 28/06/2017 run1 True sample 6,13 53444 0 0.00
S64 S64 K4 V4-SA711 V3-SA504 Bosc Field France Whole Culex pipiens E15 0 28/06/2017 run1 True sample 4,15 47628 0 0.00
S79 S79 B6 V4-SA702 V3-SA506 Camping Europe Field France Ovary Culex pipiens J16 12 28/06/2017 run1 True sample 33,8 59755 0 0.00
S80 S80 C6 V4-SA703 V3-SA506 Camping Europe Field France Ovary Culex pipiens J17 13 28/06/2017 run1 True sample 4,58 52788 0 0.00
S83 S83 F6 V4-SA706 V3-SA506 Camping Europe Field France Ovary Culex pipiens J20 16 28/06/2017 run1 True sample 35,5 42272 0 0.00
S84 S84 G6 V4-SA707 V3-SA506 Camping Europe Field France Ovary Culex pipiens J21 17 28/06/2017 run1 True sample 21 56676 0 0.00
S85 S85 H6 V4-SA708 V3-SA506 Camping Europe Field France Ovary Culex pipiens J22 18 28/06/2017 run1 True sample 11,6 41690 0 0.00
S86 S86 I6 V4-SA709 V3-SA506 Camping Europe Field France Ovary Culex pipiens J23 19 28/06/2017 run1 True sample 4,14 61984 0 0.00
S87 S87 J6 V4-SA710 V3-SA506 Bosc Field France Ovary Culex pipiens J24 20 28/06/2017 run1 True sample 28,1 65958 0 0.00
S88 S88 K6 V4-SA711 V3-SA506 Bosc Field France Ovary Culex pipiens J25 21 28/06/2017 run1 True sample 8,6 53102 0 0.00 
# replace metadata in the created phyloseq object
sample_data(ps) <- sample_data(new.metadata)

Taxonomic structure

Count

col <- brewer.pal(7, "Pastel2")

# reshape data for plot
test3 <- test %>% select(c(Sample, Species, Location, Organ, Read_depth, Read_asaia)) %>% reshape2::melt(id.vars=c("Sample", "Species", "Location", "Organ"), vars=c("Read_depth", "Read_asaia"))

count_whole <- test3[test3$Organ=="Whole",]
count_ovary <- test3[test3$Organ=="Ovary",]

make.italic <- function(x) as.expression(lapply(x, function(y) bquote(italic(.(y)))))

levels(count_whole$Species)= c("Aedes aegypti"=make.italic("Aedes aegypti"),
               "Culex pipiens"=make.italic("Culex pipiens"),
               "Culex quinquefasciatus"=make.italic("Culex quinquefasciatus"))

levels(count_ovary$Species)= c("Aedes aegypti"=make.italic("Aedes aegypti"),
               "Culex pipiens"=make.italic("Culex pipiens"),
               "Culex quinquefasciatus"=make.italic("Culex quinquefasciatus"))

levels(count_whole$Location) <- c("Bosc", "Camping~Europe", "Guadeloupe", "Lavar~(lab)", expression(paste(italic("Wolbachia"), "- (Slab TC)")))

levels(count_ovary$Location) <- c("Bosc", "Camping~Europe", "Guadeloupe", "Lavar~(lab)", expression(paste(italic("Wolbachia"), "- (Slab TC)")))


# plot
p_count1 <- ggplot(count_whole, aes(x = Sample, y = value, fill=variable))+ 
  geom_bar(position = "dodge", stat = "identity")+
  scale_fill_manual(values = col)+
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, size=12, hjust=1, vjust=0.5)) +
  ggtitle("") + 
  guide_italics+
  theme(legend.title = element_text(size = 20), 
        legend.position="bottom",
        legend.text=element_text(size=14), 
        panel.spacing.y=unit(1, "lines"), 
        panel.spacing.x=unit(0.8, "lines"),
        panel.spacing=unit(0,"lines"),
        strip.background=element_rect(color="grey30", fill="grey90"),
        strip.text.x = element_text(size = 16),
        panel.border=element_rect(color="grey90"),
        axis.ticks.x=element_blank(),
        axis.text.y = element_text(size=18)) +
  facet_wrap(~Species+Location+Organ, scales = "free_x", ncol=3, labeller=label_parsed)+
  labs(y="Sequence counts")+
  ylim(0, 900000)+
  geom_text(aes(label=value), position=position_dodge(width=1.1), width=0.25, size=4, hjust=-0.25, vjust=0.5, angle=90)+
  guides(fill=guide_legend(title="Read"))
## Warning: Ignoring unknown parameters: width
p_count2 <- ggplot(count_ovary, aes(x = Sample, y = value, fill=variable))+ 
  geom_bar(position = "dodge", stat = "identity")+
    scale_fill_manual(values = col)+
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, size=18, hjust=1, vjust=0.5)) +
  ggtitle("") + 
  guide_italics+
  theme(legend.title = element_text(size = 20), 
        legend.position="bottom",
        legend.text=element_text(size=14), 
        panel.spacing.y=unit(1, "lines"), 
        panel.spacing.x=unit(0.8, "lines"),
        panel.spacing=unit(0,"lines"),
        strip.background=element_rect(color="grey30", fill="grey90"),
        strip.text.x = element_text(size = 16),
        panel.border=element_rect(color="grey90"),
        axis.ticks.x=element_blank(),
        axis.text.y = element_text(size=18)) +
 facet_wrap(~Species+Location+Organ, scales = "free_x", ncol=3, labeller=label_parsed)+
  labs(y="Sequence counts")+
    ylim(0, 900000)+
  geom_text(aes(label=value), position=position_dodge(width=0.8), width=0.25, size=4, hjust=-0.25, vjust=0.5, angle=90)+
  guides(fill=guide_legend(title="Read"))
## Warning: Ignoring unknown parameters: width
# afficher plot
p_count1
## Warning: position_dodge requires non-overlapping x intervals
## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

p_count2

# panels
p_group <- plot_grid(p_count1+theme(legend.position="none"), 
          p_count2+theme(legend.position="none"), 
          nrow=2, 
          ncol=1)+
    draw_plot_label(c("B1", "B2"), c(0, 0), c(1, 0.5), size = 20)
## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals
legend_plot <- get_legend(p_count1 + theme(legend.position="bottom"))
## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals

## Warning: position_dodge requires non-overlapping x intervals
p_counts <- plot_grid(p_group, legend_plot, nrow=2, ncol=1, rel_heights = c(1, .1))
p_counts

Whole (the most abundant nodes)

guide_italics <- guides(fill = guide_legend(label.theme = element_text(size = 16, face = "italic", colour = "Black", angle = 0), nrow=3, byrow=TRUE))

# select whole
ps.filter.whole <- subset_samples(ps, Organ=="Whole")
ps.filter.whole <- prune_taxa(taxa_sums(ps.filter.whole) >= 1, ps.filter.whole)
ps.filter.whole <- prune_samples(sample_sums(ps.filter.whole) >= 1, ps.filter.whole)
ps.filter.whole
## phyloseq-class experiment-level object
## otu_table()   OTU Table:         [ 5 taxa and 57 samples ]
## sample_data() Sample Data:       [ 57 samples by 18 sample variables ]
## tax_table()   Taxonomy Table:    [ 5 taxa by 1 taxonomic ranks ]
# data pour plot
data_for_plot2 <- taxo_data_fast(ps.filter.whole, method = "abundance")
## Warning in `[<-.factor`(`*tmp*`, ri, value = "Other"): invalid factor level, NA
## generated
paste0("\n15 MOST ABUNDANT GENUS: \n") %>% cat()
## 
## 15 MOST ABUNDANT GENUS:
paste0("\"", levels(data_for_plot2$Name), "\",\n") %>% cat()
## "oligotype_CATAG (16) | size:661010 / N1156 (40) | size:622340.",
##  "oligotype_CATGG (8) | size:4619 / N0492 (18) | size:6153.",
##  "oligotype_TACGA (68) | size:376837 / N0939 (68) | size:364329.",
##  "oligotype_TGCGA (33) | size:699320 / N1147 (33) | size:651167.",
##  "oligotype_TGCGG (10) | size:5016 / N1146 (10) | size:4924.",
##  "Other.",
new_names <- c("oligotype_TGCGA (33) | size:699320 / N1147 (33) | size:651167.",
               "oligotype_CATAG (16) | size:661010 / N1156 (40) | size:622340.",
               "oligotype_TACGA (68) | size:376837 / N0939 (68) | size:364329.",
               "oligotype_TGCGG (10) | size:5016 / N1146 (10) | size:4924.",
               "oligotype_CATGG (8) | size:4619 / N0492 (18) | size:6153.",
               "Other.")


data_for_plot2$Name <- factor(data_for_plot2$Name, levels = new_names)

col_add <- brewer.pal(8, "Accent")


col <- c("oligotype_TGCGA (33) | size:699320 / N1147 (33) | size:651167."="#CDDE8E",
         "oligotype_CATAG (16) | size:661010 / N1156 (40) | size:622340."="#DDFFC4",
         "oligotype_TACGA (68) | size:376837 / N0939 (68) | size:364329."="#A6DE45",
         "oligotype_TGCGG (10) | size:5016 / N1146 (10) | size:4924."=col_add[1],
         "oligotype_CATGG (8) | size:4619 / N0492 (18) | size:6153."=col_add[2],
         "Other."="#A0A0A0")

levels(data_for_plot2$Species)= c("Aedes aegypti"=make.italic("Aedes aegypti"),
               "Culex pipiens"=make.italic("Culex pipiens"),
               "Culex quinquefasciatus"=make.italic("Culex quinquefasciatus"))

levels(data_for_plot2$Location) <- c("Bosc", "Camping~Europe", "Guadeloupe", "Lavar~(lab)", expression(paste(italic("Wolbachia"), "- (Slab TC)")))

data_for_plot2 <- data_for_plot2 %>% na.omit()

p2 <- ggplot(data_for_plot2, aes(x = Sample, y = Relative_Abundance, fill = Name, species=Species, organ=Organ, location=Location))+ 
  geom_bar(position = "stack", stat = "identity")+
  scale_fill_manual(values = col)+
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, size=18, hjust=1, vjust=0.5)) +
  ggtitle("")+
  guide_italics+
  theme(legend.title = element_text(size = 20),
        legend.position="bottom",
        legend.text = element_text(size=14),
        #legend.key.height = unit(1, 'cm'),
        panel.spacing.y=unit(1, "lines"),
        panel.spacing.x=unit(0.8, "lines"),
        panel.spacing=unit(0,"lines"),
        strip.background=element_rect(color="grey30", fill="grey90"),
        strip.text.x = element_text(size = 16),
        panel.border=element_rect(color="grey90"),
        axis.ticks.x=element_blank(),
        axis.text.y = element_text(size=18)) +
  facet_wrap(~Species+Location+Organ, scales = "free", ncol=3, labeller=label_parsed)+
  labs(x="Sample", y="Relative abundance", fill="Oligotype / MED node")

p2

Ovary (the most abundant nodes)

# select ovary
ps.filter.ovary <- subset_samples(ps, Organ=="Ovary")
ps.filter.ovary <- prune_taxa(taxa_sums(ps.filter.ovary) >= 1, ps.filter.ovary)
ps.filter.ovary <- prune_samples(sample_sums(ps.filter.ovary) >= 1, ps.filter.ovary)
ps.filter.ovary
## phyloseq-class experiment-level object
## otu_table()   OTU Table:         [ 3 taxa and 8 samples ]
## sample_data() Sample Data:       [ 8 samples by 18 sample variables ]
## tax_table()   Taxonomy Table:    [ 3 taxa by 1 taxonomic ranks ]
# data pour plot
data_for_plot3 <- taxo_data_fast(ps.filter.ovary, method="abundance")
## Warning in `[<-.factor`(`*tmp*`, ri, value = "Other"): invalid factor level, NA
## generated
paste0("\n15 MOST ABUNDANT GENUS: \n") %>% cat()
## 
## 15 MOST ABUNDANT GENUS:
paste0("\"", levels(data_for_plot3$Name), "\",\n") %>% cat()
## "oligotype_CATAG (16) | size:661010 / N1156 (40) | size:622340.",
##  "oligotype_TACGA (68) | size:376837 / N0939 (68) | size:364329.",
##  "oligotype_TGCGA (33) | size:699320 / N1147 (33) | size:651167.",
##  "Other.",
new_names <- c("oligotype_TGCGA (33) | size:699320 / N1147 (33) | size:651167.",
               "oligotype_CATAG (16) | size:661010 / N1156 (40) | size:622340.",
               "oligotype_TACGA (68) | size:376837 / N0939 (68) | size:364329.",
               "Other."
)

data_for_plot3$Name <- factor(data_for_plot3$Name, levels = new_names)

levels(data_for_plot3$Species)= c("Aedes aegypti"=make.italic("Aedes aegypti"),
               "Culex pipiens"=make.italic("Culex pipiens"),
               "Culex quinquefasciatus"=make.italic("Culex quinquefasciatus"))

levels(data_for_plot3$Location) <- c("Bosc", "Camping~Europe", "Guadeloupe", "Lavar~(lab)", expression(paste(italic("Wolbachia"), "- (Slab TC)")))

data_for_plot3 <- data_for_plot3 %>% na.omit()

p3 <- ggplot(data_for_plot3, aes(x = Sample, y = Relative_Abundance, fill = Name, species=Species, organ=Organ, location=Location))+ 
  geom_bar(position = "stack", stat = "identity")+
  scale_fill_manual(values = col)+
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90, size=18, hjust=1, vjust=0.5)) +
  ggtitle("") + 
  guide_italics+
  theme(legend.title = element_text(size = 20), 
        legend.position="bottom",
        legend.text = element_text(size=14),
        #legend.key.height = unit(1, 'cm'),
        panel.spacing.y=unit(1, "lines"), 
        panel.spacing.x=unit(0.8, "lines"),
        panel.spacing=unit(0,"lines"),
        strip.background=element_rect(color="grey30", fill="grey90"),
        strip.text.x = element_text(size = 16),
        panel.border=element_rect(color="grey90"),
        axis.ticks.x=element_blank(),
        axis.text.y = element_text(size=18)) +
  facet_wrap(~Species+Location+Organ, scales = "free", ncol=3, labeller=label_parsed)+
  labs(x="Sample", y="Relative abundance", fill="Oligotype / MED node")

p3

Panels taxonomy of whole / ovary

legend_plot <- get_legend(p2 + theme(legend.position="bottom"))

# panels
p_group <- plot_grid(p2+theme(legend.position="none"), 
          p3+theme(legend.position="none"), 
          nrow=2, 
          ncol=1)+
    draw_plot_label(c("A1", "A2"), c(0, 0), c(1, 0.5), size = 20)

p_taxo <- plot_grid(p_group, legend_plot, nrow=2, rel_heights = c(1, .1))
p_taxo

Save taxonomic plot

setwd(path_plot)

tiff("2Db_OLIGO_counts_asaia.tiff", units="in", width=20, height=18, res=300)
p_counts
dev.off()
## quartz_off_screen 
##                 2
tiff("2Db_OLIGO_taxonomic_asaia_whole.tiff", units="in", width=16, height=12, res=300)
p2
dev.off()
## quartz_off_screen 
##                 2
tiff("2Db_OLIGO_taxonomic_asaia_ovary.tiff", units="in", width=18, height=14, res=300)
p3
dev.off()
## quartz_off_screen 
##                 2
tiff("2Db_OLIGO_taxonomic_asaia.tiff", units="in", width=18, height=16, res=300)
p_taxo
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_counts_asaia_big.png", units="in", width=20, height=18, res=300)
p_counts
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_counts_asaia_small.png", units="in", width=18, height=14, res=300)
p_counts
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_taxonomic_asaia_whole.png", units="in", width=16, height=12, res=300)
p2
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_taxonomic_asaia_ovary.png", units="in", width=18, height=14, res=300)
p3
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_taxonomic_asaia_big.png", units="in", width=18, height=18, res=300)
p_taxo
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_taxonomic_asaia_small.png", units="in", width=18, height=14, res=300)
p_taxo
dev.off()
## quartz_off_screen 
##                 2

Make main plot

setwd(paste0(path_oligo,"/asaia/oligotyping_Asaia_sequences-c5-s1-a0.0-A0-M10/HTML-OUTPUT"))

img <- magick::image_read("entropy.png")
p_entropy <- magick::image_ggplot(img, interpolate = TRUE)
p_entropy+ theme(plot.margin = unit(c(-7,-2.5,-7,-0.5), "cm"))

p_entropy+ theme(plot.margin=unit(c(-7,-2,-12,-5), "mm"))

aligned <- plot_grid(p_taxo, 
                     p_counts, 
                     align="hv")

aligned

p_entropy2 <- plot_grid(p_entropy, nrow=1)+
  draw_plot_label(c("C"), c(0), c(1), size=20, hjust=-0.5)

p_entropy2

t_plot <- plot_grid(aligned, 
                    p_entropy2,
                    nrow=2, 
                    ncol=1, 
                    scale=1,
                    rel_heights=c(2,1))

t_plot

setwd(path_plot)

tiff("2Db_OLIGO_main_asaia.tiff", width=36, height=36, res=300, units="in")
t_plot
dev.off()
## quartz_off_screen 
##                 2
png("2Db_OLIGO_main_asaia.png", width=36, height=36, res=300, units="in")
t_plot
dev.off()
## quartz_off_screen 
##                 2